Challenges in Explaining Pretrained Clinical Text Classifiers

ArXi:2605.28060v1 Announce Type: new Explaining the predictions of neural models in clinical NLP remains a significant challenge, especially for complex tasks involving long, unstructured medical texts. While post-hoc methods like LIME and SHAP are widely used, they often fall short when applied to clinical narratives. In this paper, we identify core limitations of token-level and perturbation-based explanation techniques through targeted nstra- tions on a hospital length-of-stay prediction task.